CN110533258A - A kind of rice wheat rotation waterlogging Forewarn evaluation method and system - Google Patents
A kind of rice wheat rotation waterlogging Forewarn evaluation method and system Download PDFInfo
- Publication number
- CN110533258A CN110533258A CN201910837494.1A CN201910837494A CN110533258A CN 110533258 A CN110533258 A CN 110533258A CN 201910837494 A CN201910837494 A CN 201910837494A CN 110533258 A CN110533258 A CN 110533258A
- Authority
- CN
- China
- Prior art keywords
- rainfall
- level
- depth
- water
- rice
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 30
- 240000000359 Triticum dicoccon Species 0.000 title claims abstract description 27
- 239000003673 groundwater Substances 0.000 claims abstract description 77
- 241000209094 Oryza Species 0.000 claims abstract description 41
- 235000007164 Oryza sativa Nutrition 0.000 claims abstract description 41
- 235000009566 rice Nutrition 0.000 claims abstract description 41
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 37
- 238000013178 mathematical model Methods 0.000 claims abstract description 32
- 238000010801 machine learning Methods 0.000 claims abstract description 27
- 241000209140 Triticum Species 0.000 claims abstract description 22
- 235000021307 Triticum Nutrition 0.000 claims abstract description 22
- 238000009395 breeding Methods 0.000 claims abstract description 9
- 230000001488 breeding effect Effects 0.000 claims abstract description 9
- 239000002352 surface water Substances 0.000 claims description 20
- 239000002689 soil Substances 0.000 claims description 13
- 241000196324 Embryophyta Species 0.000 claims description 7
- 238000013527 convolutional neural network Methods 0.000 claims description 7
- 238000007637 random forest analysis Methods 0.000 claims description 7
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 238000011160 research Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000007717 exclusion Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000005094 computer simulation Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000003967 crop rotation Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000019771 cognition Effects 0.000 description 1
- 230000000536 complexating effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012279 drainage procedure Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000001556 precipitation Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Marine Sciences & Fisheries (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Animal Husbandry (AREA)
- General Health & Medical Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- Mining & Mineral Resources (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention discloses a kind of rice wheat rotation waterlogging Forewarn evaluation method and system.This method comprises: obtaining history meteorological data；Machine learning method is used according to the history meteorological data, establishes rainfall mathematical model；Obtain the rainfall product data of the following setting number of days；According to the rainfall product data and the rainfall mathematical model, the following field level depth of water or level of ground water are predicted；The permission flooding depth and Mai Ji for obtaining rice each breeding time allow highest level of ground water；Judge whether the ground depth of water is more than the permission flooding depth or whether level of ground water is more than to allow highest level of ground water；If so, publication warning information, and calculate the underproduction rate of rice or wheat；According to the underproduction rate, waterlogged disaster is assessed；If it is not, not issuing warning information then.By means of the present invention or system can be improved the ability of agricultural disaster forecasting and warning and preferably accurately be assessed waterlogged disaster.
Description
Technical field
The present invention relates to disaster alarm field, more particularly to a kind of rice wheat rotation waterlogging Forewarn evaluation method and
System.
Background technique
China is the serious uneven country of a distribution of water resources space-time, and southern area takes place frequently in rainy season waterlogged disaster, In
While causing huge economic loss, the further development of agricultural is also counteracted.However, people are for flooded stain calamity at present
Harmful cognition remains wretched insufficiency, and waterlogging disaster is that rainfall, land surface condition and crops ring waterlogged disaster
Answer the complexing actions such as characteristic as a result, it is difficult to assess and predict, the evaluation problem of waterlogging disaster has to be solved.And rice and kernel
Crop rotation is a kind of important crop rotation method in China farmland, and area accounts for 1/5 of rice field area or so, therefore, develops one kind
The method assessed early warning and assess rice wheat rotation waterlogging disaster is necessary.
Currently, country and government also focus on the development of disaster alarm technology further.For example, national synthetic disaster prevention rule
It draws in (2016-the year two thousand twenty) and just explicitly points out, reinforce disaster monitoring forecasting and warning and risk preventing ability is built, improve disaster
Accuracy, the timeliness of warning information publication；Reinforce engineering to prevent and reduce natural disasters capacity building.
Research at present in terms of waterlogging damage control is less, and it is existing to have device and method mostly concern improvement
Farmland ditch and Irrigation etc., as Chinese patent CN102031768B is disclosed, a kind of novel farmland flood stain is anti-to purchase things necessary for a long journey
It sets and its application technology, but needs to construct multilevel drainage device and control of groundwater level device, lack for the following flooded stain calamity
Harmful forecasting and warning and assessment, device complexity, high investment, is also difficult to promote the use of in China in a short time.
Summary of the invention
The object of the present invention is to provide a kind of rice wheat rotation waterlogging Forewarn evaluation method and system, can be improved agriculture
The ability of industry hazard forecasting early warning and preferably waterlogged disaster is accurately assessed.
To achieve the above object, the present invention provides following schemes:
A kind of rice wheat rotation waterlogging Forewarn evaluation method, comprising:
Obtain history meteorological data；
Machine learning method is used according to the history meteorological data, establishes rainfall mathematical model；
Obtain the rainfall product data of the following setting number of days；
According to the rainfall product data and the rainfall mathematical model, the following field level depth of water or underground water are predicted
Position；
The permission flooding depth and Mai Ji for obtaining rice each breeding time allow highest level of ground water；
Judge whether the ground depth of water is more than the permission flooding depth or whether level of ground water is more than to allow superlatively
Lower water level；
If so, publication warning information, and calculate the underproduction rate of rice or wheat；
According to the underproduction rate, waterlogged disaster is assessed；
If it is not, not issuing warning information then.
Optionally, the acquisition history meteorological data, specifically includes:
Obtain history flood data and Storm Flood Disasters In China data set.
Optionally, described that machine learning method is used according to the history meteorological data, rainfall mathematical model is established, is had
Body includes:
Machine learning method is used according to the history meteorological data, establishes rainfall mathematical model R=f (d, c)+Δ R,
Wherein, R is history rainfall, and d is that Soil surface water is deep, and c is level of ground water, Δ R be the Soil surface water depth d obtained according to the last time and
The rainfall R that the level of ground water c that last time obtains is calculated1With actual history rainfall R0Difference；
The machine learning method is using any one in convolutional neural networks method, support vector machines or random forest method.
Optionally, the rainfall product data for obtaining the following setting number of days, specifically includes:
It is obtained not from Chinese weather wisdom cloud platform or OpenWeatherMap meteorological data website using crawler method
Set the rainfall product data of number of days, the number of days that sets is 5 day, 6 days or 7 days.
Optionally, the underproduction rate for calculating rice or wheat, specifically includes:
Using formulaCalculate the flooded stain underproduction rate of rice；
Wherein, Y0For the underproduction rate of crop, m, n, k are parameter, and H is Plant Height of Rice, and h is flooding depth, when T is waterflooding
Between, H0Lower limit is lost for crop waterflooding；
Or use formulaCalculate the flooded stain underproduction rate of wheat；
Wherein, a, b, c are parameter, and e is that level of ground water returns the number of days for being down to control buried depth, lcIt is buried for setting level of ground water
It is deep, dtFor the groundwater level depth after surface water exclusion the t days.
A kind of rice wheat rotation waterlogging Forewarn evaluation system, comprising:
First obtains module, for obtaining history meteorological data；
Rainfall mathematical model establishes module, for using machine learning method according to the history meteorological data, establishes drop
Rainfall mathematical model；
Second obtains module, for obtaining the rainfall product data of the following setting number of days；
Prediction module, for predicting the following field level according to the rainfall product data and the rainfall mathematical model
The depth of water or level of ground water；
Third obtains module, and the permission flooding depth and Mai Ji for obtaining rice each breeding time allow highest underground water
Position；
Judgment module, for judge the ground depth of water whether be more than the permission flooding depth or level of ground water whether
More than permission highest level of ground water；
Warning module is more than to allow most for working as the ground depth of water more than the permission flooding depth or level of ground water
Warning information is issued when phreatic high；Or when the ground depth of water is no more than the permission flooding depth and level of ground water not
Warning information is not issued when more than permission highest level of ground water；
Underproduction rate computing module, for calculating the underproduction rate of rice or wheat；
Evaluation module, for assessing waterlogged disaster according to the underproduction rate.
Optionally, described first module is obtained, specifically included:
First acquisition unit, for obtaining history flood data and Storm Flood Disasters In China data set.
Optionally, the rainfall mathematical model establishes module, specifically includes:
Rainfall mathematical model establishes unit, for using machine learning method according to the history meteorological data, establishes drop
Rainfall mathematical model R=f (d, c)+Δ R, wherein R is history rainfall, and d is that Soil surface water is deep, and c is level of ground water, and Δ R is root
The rainfall R that the Soil surface water depth d and last obtained level of ground water c obtained according to the last time is calculated1It is dropped with actual history
Rainfall R0Difference；
The machine learning method is using any one in convolutional neural networks method, support vector machines or random forest method.
Optionally, described second module is obtained, specifically included:
Second acquisition unit, for using crawler method from Chinese weather wisdom cloud platform or OpenWeatherMap gas
The rainfall product data of the following setting number of days is obtained on image data website, the number of days that sets is 5 day, 6 days or 7 days.
Optionally, the underproduction rate computing module, specifically includes:
Underproduction rate computing unit, for using formulaCalculate rice
Flooded stain underproduction rate；
Wherein, Y0For the underproduction rate of crop, m, n, k are parameter, and H is Plant Height of Rice, and h is flooding depth, when T is waterflooding
Between, H0Lower limit is lost for crop waterflooding；
Or use formulaCalculate the flooded stain underproduction rate of wheat；
Wherein, a, b, c are parameter, and e is that level of ground water returns the number of days for being down to control buried depth, lcIt is buried for setting level of ground water
It is deep, dtFor the groundwater level depth after surface water exclusion the t days.
The specific embodiment provided according to the present invention, the invention discloses following technical effects:
The present invention provides a kind of rice wheat rotation waterlogging Forewarn evaluation method, comprising: obtains history meteorological data；Root
Machine learning method is used according to the history meteorological data, establishes rainfall mathematical model；Obtain the rainfall of the following setting number of days
Data；According to the rainfall product data and the rainfall mathematical model, the following field level depth of water or level of ground water are predicted；
The permission flooding depth and Mai Ji for obtaining rice each breeding time allow highest level of ground water；Judge whether the ground depth of water surpasses
Cross whether the permission flooding depth or level of ground water are more than to allow highest level of ground water；If so, publication warning information, and
Calculate the underproduction rate of rice or wheat；According to the underproduction rate, waterlogged disaster is assessed；If it is not, not issuing warning information then.It is logical
Crossing the above method can be improved the ability of agricultural disaster forecasting and warning and is preferably accurately assessed waterlogged disaster.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be in embodiment
Required attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some realities of the invention
Example is applied, it for those of ordinary skill in the art, without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is rice wheat rotation waterlogging Forewarn evaluation method flow diagram of the present invention；
Fig. 2 is rice wheat rotation waterlogging Forewarn evaluation system construction drawing of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts it is all its
His embodiment, shall fall within the protection scope of the present invention.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Fig. 1 is rice wheat rotation waterlogging Forewarn evaluation method flow diagram of the present invention.As shown in Figure 1, a kind of rice wheat rotation
Waterlogging Forewarn evaluation method includes:
Step 101: history meteorological data is obtained, is specifically included:
Obtain history flood data and Storm Flood Disasters In China data set.
Step 102: machine learning method is used according to the history meteorological data, establishes rainfall mathematical model, it is specific to wrap
It includes:
Machine learning method is used according to the history meteorological data, establishes rainfall mathematical model R=f (d, c)+Δ R,
Wherein, R is history rainfall, and d is that Soil surface water is deep, and c is level of ground water, Δ R be the Soil surface water depth d obtained according to the last time and
The rainfall R that the level of ground water c that last time obtains is calculated1With actual history rainfall R0Difference；Here using
Theoretical rainfall R one day after is calculated in iterative algorithm, d, c with the f relational expression of the first day and one day after1It calculates and goes through
Practical rainfall R in history0Difference.
The machine learning method is using any one in convolutional neural networks method, support vector machines or random forest method.
The machine learning method can be trained model with data such as different rainfall intensities, the different fields depth of waters, propose phase
The pre- precipitation position of prediction scheme such as engineering is answered, provides support by flooded stain early warning for the scheduling of the engineerings such as lock station.
Step 103: the rainfall product data of the following setting number of days is obtained, is specifically included:
It is obtained not from Chinese weather wisdom cloud platform or OpenWeatherMap meteorological data website using crawler method
Set the rainfall product data of number of days, the number of days that sets is 5 day, 6 days or 7 days.
Step 104: according to the rainfall product data and the rainfall mathematical model, predicting the following field level depth of water
Or level of ground water；
Step 105: the permission flooding depth and Mai Ji for obtaining rice each breeding time allow highest level of ground water；
Step 106: judging whether the ground depth of water is more than the permission flooding depth or whether level of ground water is more than fair
Perhaps highest level of ground water；
Step 107: if so, publication warning information, and calculate the underproduction rate of rice or wheat.
The underproduction rate for calculating rice or wheat, specifically includes:
Using formulaCalculate the flooded stain underproduction rate of rice；
Wherein, Y0For the underproduction rate of crop, m, n, k are parameter, and H is Plant Height of Rice, and h is flooding depth, when T is waterflooding
Between, H0Lower limit is lost for crop waterflooding；
Or use formulaCalculate the flooded stain underproduction rate of wheat；
Wherein, a, b, c are parameter, and e is that level of ground water returns the number of days for being down to control buried depth, lcIt is buried for setting level of ground water
It is deep, dtFor the groundwater level depth after surface water exclusion the t days.
Step 108: according to the underproduction rate, assessing waterlogged disaster；The index of the assessment waterlogged disaster refers to, distinguishes
Obtain rice wheat rotation farmland rice season under rice different growing field face flooding depth and damage or crop failure caused by waterlogging between relationship, Mai Ji it is small
Relationship between wheat level of ground water and stain evil, establishes its vulnerability index further according to crop cut yield and crop average market price,
To assess rice wheat rotation waterlogging disaster.
Step 109: if it is not, not issuing warning information then.
Fig. 2 is rice wheat rotation waterlogging Forewarn evaluation system construction drawing of the present invention.As shown in Fig. 2, a kind of rice wheat rotation
Waterlogging Forewarn evaluation system includes:
First obtains module 201, for obtaining history meteorological data；
Rainfall mathematical model establishes module 202, for using machine learning method according to the history meteorological data, builds
Vertical rainfall mathematical model；
Second obtains module 203, for obtaining the rainfall product data of the following setting number of days；
Prediction module 204, for predicting the following field according to the rainfall product data and the rainfall mathematical model
The ground depth of water or level of ground water；
Third obtains module 205, under permission flooding depth and Mai Ji for obtaining rice each breeding time allow superlatively
Water level；
Judgment module 206, for judging whether the ground depth of water is more than the permission flooding depth or level of ground water is
No is more than to allow highest level of ground water；
Warning module 207, for being more than the permission flooding depth or level of ground water more than permission when the ground depth of water
Warning information is issued when highest level of ground water；Or when the ground depth of water is no more than the permission flooding depth and level of ground water
Warning information is not issued when no more than permission highest level of ground water；
Underproduction rate computing module 208, for calculating the underproduction rate of rice or wheat；
Evaluation module 209, for assessing waterlogged disaster according to the underproduction rate.
Described first obtains module 201, specifically includes:
First acquisition unit, for obtaining history flood data and Storm Flood Disasters In China data set.
The rainfall mathematical model establishes module 202, specifically includes:
Rainfall mathematical model establishes unit, for using machine learning method according to the history meteorological data, establishes drop
Rainfall mathematical model R=f (d, c)+Δ R, wherein R is history rainfall, and d is that Soil surface water is deep, and c is level of ground water, and Δ R is root
The rainfall R that the Soil surface water depth d and last obtained level of ground water c obtained according to the last time is calculated1It is dropped with actual history
Rainfall R0Difference；
The machine learning method is using any one in convolutional neural networks method, support vector machines or random forest method.
Described second obtains module 203, specifically includes:
Second acquisition unit, for using crawler method from Chinese weather wisdom cloud platform or OpenWeatherMap gas
The rainfall product data of the following setting number of days is obtained on image data website, the number of days that sets is 5 day, 6 days or 7 days.
The underproduction rate computing module 208, specifically includes:
Underproduction rate computing unit, for using formulaCalculate rice
Flooded stain underproduction rate；
Wherein, Y0For the underproduction rate of crop, m, n, k are parameter, and H is Plant Height of Rice, and h is flooding depth, when T is waterflooding
Between, H0Lower limit is lost for crop waterflooding；
Or use formulaCalculate the flooded stain underproduction rate of wheat；
Wherein, a, b, c are parameter, and e is that level of ground water returns the number of days for being down to control buried depth, lcIt is buried for setting level of ground water
It is deep, dtFor the groundwater level depth after surface water exclusion the t days.
Embodiment 1:
The typical protective embankments in lakeside areas area for selecting the middle and lower reach of Yangtze River easily flood easily stain area Hubei Qianjiang is research object, collects trial zone
History is meteorological, waterlogged disaster data, training machine learning method carries out quick early warning and publication to agriculture district waterlogged disaster, together
When, flooded stain dynamic simulation model is driven, realizes waterlogging process simulation；Research area difference causes the condition of a disaster scape, drives farmland
Flooded stain process simulation model proposes emergency preplan.
The data such as collection research area landform, water system, hydraulic engineering, land use and history flood stain the condition of a disaster first.History
Flooded stain the condition of a disaster data mainly include the history meteorological data (number such as history rainfall date, rainfall, rainfall duration, raindrop type
According to), history waterlogged disaster loss data and history socioeconomic data, pump lock engineering operation data etc..
Using easily flood easily stain area Hubei Qianjiang as research object, typical protective embankments in lakeside areas area is selected to carry out the farmland-gutter pool-area
The multiple dimensioned waterlogging process multiple component detection test in domain-country fair area.Farmland mainly monitors typical Rainfall process and drainage procedure
The data such as data, farmland surface water layer, soil moisture, level of ground water；The gutter pool mainly monitors water level and rate of discharge；Area
The area Yu Hexu mainly monitors river node stage-discharge and Outlet Section water level and flow.
It is as follows that the flooded stain of rice subtracts productivity function:
Wherein, Y0For the underproduction rate of crop, m, n, k are parameter, and H is Plant Height of Rice, and h is flooding depth, when T is waterflooding
Between, H0Lower limit is lost for crop waterflooding.
The flooded stain of wheat subtracts productivity function are as follows:
Wherein, a, b, c are parameter, and e is that level of ground water returns the number of days (d) for being down to control buried depth, lcTo set level of ground water
Buried depth, dtFor the groundwater level depth after surface water exclusion the t days.
Underproduction risk index are as follows:
Wherein, IyFor underproduction rate risk index, YiRepresent different grades of underproduction rate, yiFor practical per unit area yield, i.e. trend produces
It measures (being obtained by model analysis), xiFor per unit area yield underproduction rate (xi< 0 is lean year), FiFor the probability that different underproduction rates occur, h is core
Window width in estimation of density function, n are sample number, and s is sample standard deviation, and Q is interquartile-range IQR.
Subtracting productivity function according to the flooded stain of the following field level depth of water, level of ground water and the rice of prediction, wheat can count
Calculate the underproduction rate of rice, wheat.
Forecasting and warning: multi-source rainfall product data library is established by multiple meteorological data websites or meteorological site.Proposed adoption
Meteorological data website includes that OpenWeatherMap, Chinese weather wisdom cloud platform etc. obtain the following rainfall forecast, wherein
The meteorological data interface of the website OpenWeatherMap can provide following 5 days every 3 hours data, and Chinese weather smart cloud is flat
Platform can provide domestic 1 × 1 kilometer and forecast by hour lattice point for 3 days.Pass through programming and web crawlers way access and research website phase
The data-interface and station address answered, it is automatic to obtain meteorological data and handled, it stores to cloud database, exploitation is short-term
Acquisition module is forecast in heavy rainfall.
" the Chinese heavy rain provided according to the experimental field history flood data and China Meteorological data network being collected into
Flood data set " and history meteorological data data, using machine learning method (such as convolutional neural networks, random forest
Deng) Rainfall Disaster under DIFFERENT METEOROLOGICAL CONDITIONS is learnt and predicted, realize that the waterlogged disaster based on intelligent algorithm is quickly pre-
Report early warning and publication.Based on the weather forecast data for being stored in cloud database of rainfall forecast acquisition module acquisition, in conjunction with intelligence
Energy learning algorithm and waterlogging dynamic simulation model predict the following Rainfall Disaster probability of happening, realize that early warning is simultaneously issued.Together
When, during real-time early warning, the reliability of same source data, meteorology of the foundation based on weight be not pre- in evaluation meteorogical phenomena database
The accuracy of Rainfall Disaster prediction is improved in measured data library.
The present invention is based on Primary Stage Data collection and site tests, establish history rainfall and field with the method for machine learning
Relationship between the depth of water and level of ground water, and by polynary short-period forecast rainfall data, predict following the field depth of water or underground water
Position, and according to the level of ground water maximum permissible value of the flooding depth permissible value of rice each breeding time and Mai Ji, judge whether to go out
Existing waterlogged disaster, thus the waterlogging hazard forecasting early warning technology that exploitation is forecast based on short-term heavy rainfall.Pass through coupling agriculture again
Field waterlogged disaster loses dynamic evaluation and optimization method, establishes efficient farmland water logging control drop stain engineering combined scheduling method, thus
Develop it is a set of integrate waterlogged disaster risk analysis, loss appraisal, snap information feedback and Analysis of Policy Making agriculture district flood stain
Calamity emergency response scheduling system.
The present invention has used the waterlogging hazard forecasting early warning technology based on short-term heavy rainfall forecast, improves flooded stain
The accuracy of hazard forecasting and the timeliness of early warning, by proposing that rice/wheat waterlogged disaster loses comprehensive estimation method, and
Method training pattern based on machine learning can be more in crawl after establishing rainfall and field water level/level of ground water relationship
After first short-period forecast rainfall data, real-time assessment prediction goes out the vulnerability of waterlogged disaster, convenient in time formulate preventative strategies and
The lock pump model for water quantity allocation in irrigated area etc..Method of the invention is feasible, convenient to carry out, and applicability is wider.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with its
The difference of his embodiment, the same or similar parts in each embodiment may refer to each other.For being disclosed in embodiment
For system, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is referring to method portion
It defends oneself bright.
Used herein a specific example illustrates the principle and implementation of the invention, above embodiments
Illustrate to be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art,
According to the thought of the present invention, there will be changes in the specific implementation manner and application range.In conclusion this specification
Content should not be construed as limiting the invention.
Claims (10)
1. a kind of rice wheat rotation waterlogging Forewarn evaluation method characterized by comprising
Obtain history meteorological data；
Machine learning method is used according to the history meteorological data, establishes rainfall mathematical model；
Obtain the rainfall product data of the following setting number of days；
According to the rainfall product data and the rainfall mathematical model, the following field level depth of water or level of ground water are predicted；
The permission flooding depth and Mai Ji for obtaining rice each breeding time allow highest level of ground water；
Judge whether the ground depth of water is more than the permission flooding depth or whether level of ground water is more than to allow highest underground water
Position；
If so, publication warning information, and calculate the underproduction rate of rice or wheat；
According to the underproduction rate, waterlogged disaster is assessed；
If it is not, not issuing warning information then.
2. rice wheat rotation waterlogging Forewarn evaluation method according to claim 1, which is characterized in that the acquisition history
Meteorological data specifically includes:
Obtain history flood data and Storm Flood Disasters In China data set.
3. rice wheat rotation waterlogging Forewarn evaluation method according to claim 1, which is characterized in that described according to
History meteorological data uses machine learning method, establishes rainfall mathematical model, specifically includes:
Machine learning method is used according to the history meteorological data, establishes rainfall mathematical model R=f (d, c)+Δ R, wherein R
For history rainfall, d is that Soil surface water is deep, and c is level of ground water, and Δ R is the Soil surface water depth d obtained according to the last time and last
To the rainfall R that is calculated of level of ground water c1With actual history rainfall R0Difference；
The machine learning method is using any one in convolutional neural networks method, support vector machines or random forest method.
4. rice wheat rotation waterlogging Forewarn evaluation method according to claim 1, which is characterized in that the acquisition future
The rainfall product data for setting number of days, specifically includes:
Being obtained future from Chinese weather wisdom cloud platform or OpenWeatherMap meteorological data website using crawler method is set
Determine the rainfall product data of number of days, the number of days that sets is 5 day, 6 days or 7 days.
5. rice wheat rotation waterlogging Forewarn evaluation method according to claim 1, which is characterized in that the calculating rice
Or the underproduction rate of wheat, it specifically includes:
Using formulaCalculate the flooded stain underproduction rate of rice；
Wherein, Y0For the underproduction rate of crop, m, n, k are parameter, and H is Plant Height of Rice, and h is flooding depth, and T is Submergence time, H0For
Lower limit is lost in crop waterflooding；
Or use formulaCalculate the flooded stain underproduction rate of wheat；
Wherein, a, b, c are parameter, and e is that level of ground water returns the number of days for being down to control buried depth, lcTo set groundwater level depth, dtFor
The surface water excludes the groundwater level depth after t days.
6. a kind of rice wheat rotation waterlogging Forewarn evaluation system characterized by comprising
First obtains module, for obtaining history meteorological data；
Rainfall mathematical model establishes module, for using machine learning method according to the history meteorological data, establishes rainfall
Mathematical model；
Second obtains module, for obtaining the rainfall product data of the following setting number of days；
Prediction module, for predicting the following field level depth of water according to the rainfall product data and the rainfall mathematical model
Or level of ground water；
Third obtains module, and the permission flooding depth and Mai Ji for obtaining rice each breeding time allow highest level of ground water；
Judgment module, for judging whether the ground depth of water is more than the permission flooding depth or whether level of ground water is more than fair
Perhaps highest level of ground water；
Warning module, for being more than the permission flooding depth or level of ground water more than under allowing superlatively when the ground depth of water
Warning information is issued when water level；Or when the ground depth of water is no more than the permission flooding depth and level of ground water no more than permission
Warning information is not issued when highest level of ground water；
Underproduction rate computing module, for calculating the underproduction rate of rice or wheat；
Evaluation module, for assessing waterlogged disaster according to the underproduction rate.
7. rice wheat rotation waterlogging Forewarn evaluation system according to claim 6, which is characterized in that described first obtains
Module specifically includes:
First acquisition unit, for obtaining history flood data and Storm Flood Disasters In China data set.
8. rice wheat rotation waterlogging Forewarn evaluation system according to claim 6, which is characterized in that the rainfall number
Model building module is learned, is specifically included:
Rainfall mathematical model establishes unit, for using machine learning method according to the history meteorological data, establishes rainfall
Mathematical model R=f (d, c)+Δ R, wherein R is history rainfall, and d is that Soil surface water is deep, and c is level of ground water, and Δ R is according to upper
The rainfall R that the Soil surface water depth d and last obtained level of ground water c once obtained is calculated1With actual history rainfall R0
Difference；
The machine learning method is using any one in convolutional neural networks method, support vector machines or random forest method.
9. rice wheat rotation waterlogging Forewarn evaluation system according to claim 6, which is characterized in that described second obtains
Module specifically includes:
Second acquisition unit, for using crawler method from Chinese weather wisdom cloud platform or OpenWeatherMap meteorological data
The rainfall product data of the following setting number of days is obtained on website, the number of days that sets is 5 day, 6 days or 7 days.
10. rice wheat rotation waterlogging Forewarn evaluation system according to claim 6, which is characterized in that the underproduction rate
Computing module specifically includes:
Underproduction rate computing unit, for using formulaCalculate the flood of rice
Stain underproduction rate；
Wherein, Y0For the underproduction rate of crop, m, n, k are parameter, and H is Plant Height of Rice, and h is flooding depth, and T is Submergence time, H0For
Lower limit is lost in crop waterflooding；
Or use formulaCalculate the flooded stain underproduction rate of wheat；
Wherein, a, b, c are parameter, and e is that level of ground water returns the number of days for being down to control buried depth, lcTo set groundwater level depth, dtFor
The surface water excludes the groundwater level depth after t days.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910837494.1A CN110533258B (en) | 2019-09-05 | 2019-09-05 | Early warning and evaluation method and system for waterlogging of rice and wheat crop rotation farmland |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910837494.1A CN110533258B (en) | 2019-09-05 | 2019-09-05 | Early warning and evaluation method and system for waterlogging of rice and wheat crop rotation farmland |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110533258A true CN110533258A (en) | 2019-12-03 |
| CN110533258B CN110533258B (en) | 2022-05-10 |
Family
ID=68666972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910837494.1A Active CN110533258B (en) | 2019-09-05 | 2019-09-05 | Early warning and evaluation method and system for waterlogging of rice and wheat crop rotation farmland |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110533258B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291478A (en) * | 2020-01-21 | 2020-06-16 | 太原理工大学 | Rainfall-runoff simulation method based on random forest algorithm |
| CN111460965A (en) * | 2020-03-27 | 2020-07-28 | 珠海欧比特宇航科技股份有限公司 | Waterlogging area intelligent analysis system and method based on unmanned aerial vehicle image |
| CN112418542A (en) * | 2020-12-03 | 2021-02-26 | 浙江知水信息技术有限公司 | Method for realizing early warning of flood conditions by machine deep learning based on meteorological data |
| CN112990108A (en) * | 2021-04-19 | 2021-06-18 | 四川省水利科学研究院 | System for realizing dam slope protection based on convolutional neural network |
| TWI806321B (en) * | 2021-12-28 | 2023-06-21 | 財團法人國家實驗研究院 | Inundation assessment method and computing device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004197554A (en) * | 2002-12-03 | 2004-07-15 | Foundation Of River & Basin Integrated Communications Japan | Real time dynamic flooding simulation system |
| CN104408900A (en) * | 2014-11-10 | 2015-03-11 | 柳州师范高等专科学校 | Dynamic optimization based neural network flood warning device and method |
| CN108052732A (en) * | 2017-12-08 | 2018-05-18 | 河海大学 | A kind of rice based on excess water process is by flooded underproduction loss late evaluation method |
| CN109255485A (en) * | 2018-09-13 | 2019-01-22 | 中国地质调查局南京地质调查中心 | Rainfall-triggered geologic hazard early-warning and predicting model and learning method based on RBFN machine learning |
-
2019
- 2019-09-05 CN CN201910837494.1A patent/CN110533258B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2004197554A (en) * | 2002-12-03 | 2004-07-15 | Foundation Of River & Basin Integrated Communications Japan | Real time dynamic flooding simulation system |
| CN104408900A (en) * | 2014-11-10 | 2015-03-11 | 柳州师范高等专科学校 | Dynamic optimization based neural network flood warning device and method |
| CN108052732A (en) * | 2017-12-08 | 2018-05-18 | 河海大学 | A kind of rice based on excess water process is by flooded underproduction loss late evaluation method |
| CN109255485A (en) * | 2018-09-13 | 2019-01-22 | 中国地质调查局南京地质调查中心 | Rainfall-triggered geologic hazard early-warning and predicting model and learning method based on RBFN machine learning |
Non-Patent Citations (4)
| Title |
|---|
| 张旭辉等: "江苏渍涝灾害气象监测预警", 《中国农学通报》 * |
| 贾茜淳等: "钟山县山洪地质灾害风险评估与预警", 《水土保持研究》 * |
| 赵思健等: "农作物气象灾害风险识别与评估研究", 《灾害学》 * |
| 黄涛珍等: "BP神经网络在洪涝灾损失快速评估中的应用", 《河海大学学报(自然科学版)》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111291478A (en) * | 2020-01-21 | 2020-06-16 | 太原理工大学 | Rainfall-runoff simulation method based on random forest algorithm |
| CN111291478B (en) * | 2020-01-21 | 2023-12-22 | 太原理工大学 | Rainfall-runoff simulation method based on random forest algorithm |
| CN111460965A (en) * | 2020-03-27 | 2020-07-28 | 珠海欧比特宇航科技股份有限公司 | Waterlogging area intelligent analysis system and method based on unmanned aerial vehicle image |
| CN111460965B (en) * | 2020-03-27 | 2024-05-31 | 珠海欧比特宇航科技股份有限公司 | Waterlogging area intelligent analysis system and method based on unmanned aerial vehicle image |
| CN112418542A (en) * | 2020-12-03 | 2021-02-26 | 浙江知水信息技术有限公司 | Method for realizing early warning of flood conditions by machine deep learning based on meteorological data |
| CN112990108A (en) * | 2021-04-19 | 2021-06-18 | 四川省水利科学研究院 | System for realizing dam slope protection based on convolutional neural network |
| TWI806321B (en) * | 2021-12-28 | 2023-06-21 | 財團法人國家實驗研究院 | Inundation assessment method and computing device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110533258B (en) | 2022-05-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110533258A (en) | A kind of rice wheat rotation waterlogging Forewarn evaluation method and system | |
| CN108022053A (en) | Flood risk assessment method and apparatus | |
| CN114252128B (en) | Underground pipe gallery water inflow monitoring and early warning system and method | |
| CN109859442A (en) | Mountain region disaster chain prediction and monitoring and warning system and implementation process | |
| Ibrakhimov | Spatial and temporal dynamics of groundwater table and salinity in Khorezm (Aral Sea Basin), Uzbekistan | |
| Elkaduwa et al. | Use of historical data as a decision support tool in watershed management: a case study of the Upper Nilwala basin in Sri Lanka | |
| Ali et al. | Climate change: Implications and adaptation of water resources in pakistan | |
| CN107563096A (en) | A kind of waterlogging modeling and analysis methods based on FCM | |
| CN209417901U (en) | Mountain flood dynamic early-warning system based on soil moisture content real time correction | |
| Nyayapathi et al. | Drought vulnerability assessment by employing the Geographical Information System and analytical hierarchy process for the Kurnool district of Andhra Pradesh, India | |
| KR102143039B1 (en) | Remote monitoring and control apparatus for the type of multi-path | |
| Huang et al. | Flood vulnerability to climate change through hydrological modeling: a case study of the Swift Current Creek watershed in western Canada | |
| Conrads et al. | Simulation of water levels and salinity in the rivers and tidal marshes in the vicinity of the Savannah National Wildlife Refuge, coastal South Carolina and Georgia | |
| CN115619211A (en) | System for improving risk prevention and control capacity of watershed reservoir group by utilizing digital twin technology | |
| CN115293241A (en) | River bank collapse early warning method and device based on multi-source data fusion | |
| CN212160921U (en) | Rainfall monitoring networking system for mountain torrent early warning | |
| De Wrachien et al. | Drainage and Land Reclamation in a Changing Environment: Overview and Challenges | |
| Wahyuddin et al. | Instrumenting GIS as smart city tools to identify the impact of tidal flood threat in the coastal zone of Pekalongan City | |
| Desta | Reservoir siltation in Ethiopia: Causes, source areas, and management options | |
| Lenka et al. | Scientific endeavours for natural resource management in India | |
| CN117831231B (en) | Method for carrying out flooding early warning on easily flooded and easily waterlogged areas | |
| Subramanian | Implementation of neural networks in flood forecasting | |
| CN117314175B (en) | Power grid system geological risk monitoring and evaluating method based on severe weather | |
| Erwanto et al. | Application of Geographic Information System For The Identification of Flood And Landslide Mitigation In Badeng Watershed | |
| Ler | Flood resilience and smart water management: implementation strategies for smart cities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |